Letta Code
Connect Letta Code to Divyam for reading files, editing code and running project commands.
You need a Divyam account and an API key. If you don't have them yet, follow Getting Started first.
Replace the shortened divyam-sw-v1-... shown in examples with your complete API key.
The examples use divyam-as/gpt-6-sol. For another model, select its current ID in your harness or copy it from Models and pricing, and check its context limit and supported features.
1. Install Letta Code
Follow the official installation instructions.
2. Add the provider
This command creates or updates the local backend's saved openai-compatible connection. It replaces any endpoint and key already stored under that name. Later local sessions that select this connection use Divyam.
Register an OpenAI-compatible connection with Divyam's URL and your key:
letta --backend local connect openai-compatible \
--base-url https://api.preview.divyam.ai/v1 \
--api-key "divyam-sw-v1-..."
The local backend stores provider settings and agent state on your computer. It does not require a Letta Cloud account.
3. Choose a model and start Letta Code
Model ID: divyam-as/gpt-6-sol. Context window: 1,050,000 tokens. Models and pricing
From your project folder, run:
letta --backend local --model openai-compatible/divyam-as/gpt-6-sol
The openai-compatible/ prefix selects the connection created above.
Hello, what are your capabilities?
Letta's generic OpenAI-compatible connection omits image content returned by its Read tool.
Check your requests
Open the Divyam console and select Logs. Your requests appear there within a few seconds, newest first, with their status, token counts and latency. Usage and Credits & Billing catch up within a few minutes.
Some clients display zero when model prices are missing. Check Credits & Billing for Divyam charges. Local dollar limits depend on the client's price and usage data.
For filters, cached-token counts and the requested-versus-routed view, see Logs and usage.